© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 11192
    Prev
    Next
    INDEX
    Explanations

    phrases related to bringing something or someone to a location or situation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "brought" and its variations, often in a context of introducing or presenting something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     spaced
    -0.61
     resistor
    -0.60
     Reserved
    -0.56
    raid
    -0.56
    john
    -0.54
    inates
    -0.52
     actionGroup
    -0.52
     Watkins
    -0.52
    ickers
    -0.52
     Casual
    -0.51
    POSITIVE LOGITS
     forth
    1.18
     forward
    1.02
    iment
    0.91
     into
    0.87
     hither
    0.83
     together
    0.82
     aboard
    0.80
     ashore
    0.78
    uph
    0.77
    iments
    0.76
    Activations Density 0.047%

    No Known Activations